{"id":20096534,"url":"https://github.com/jianzhnie/scalerl","last_synced_at":"2025-03-02T16:28:05.738Z","repository":{"id":258073039,"uuid":"872830307","full_name":"jianzhnie/ScaleRL","owner":"jianzhnie","description":"ScaleRL is a  simple and scalable  distributed reinforcement learning framework based on Python and PyTorch ","archived":false,"fork":false,"pushed_at":"2024-10-30T02:28:52.000Z","size":226,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-10-30T05:01:45.943Z","etag":null,"topics":["a3c","distributed-systems","dppo","impala","parallel-computing","seed-rl"],"latest_commit_sha":null,"homepage":"https://jianzhnie.github.io/llmtech/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jianzhnie.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-10-15T06:37:13.000Z","updated_at":"2024-10-30T02:28:57.000Z","dependencies_parsed_at":"2024-11-06T10:43:00.230Z","dependency_job_id":"e923e3b3-6b4c-4c2c-9ca8-e0fca046c77d","html_url":"https://github.com/jianzhnie/ScaleRL","commit_stats":null,"previous_names":["jianzhnie/scalerl"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jianzhnie%2FScaleRL","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jianzhnie%2FScaleRL/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jianzhnie%2FScaleRL/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jianzhnie%2FScaleRL/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jianzhnie","download_url":"https://codeload.github.com/jianzhnie/ScaleRL/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241536113,"owners_count":19978284,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["a3c","distributed-systems","dppo","impala","parallel-computing","seed-rl"],"created_at":"2024-11-13T16:59:09.876Z","updated_at":"2025-03-02T16:28:05.715Z","avatar_url":"https://github.com/jianzhnie.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ScaleRL\n\nScaleRL is a simple and scalable distributed reinforcement learning framework based on Python and PyTorch\n\n### Distributed RL Libraries\n\n- https://github.com/ray-project/ray\n- https://github.com/pytorch/rl\n- https://github.com/facebookresearch/torchbeast\n- https://github.com/facebookresearch/rlmeta\n- https://github.com/alex-petrenko/sample-factory\n- https://github.com/sjtu-marl/malib.git\n- https://github.com/Replicable-MARL/MARLlib\n- https://github.com/seolhokim/DistributedRL-Pytorch-Ray.git\n\n### Distributed RL Blogs\n\n- https://www.jiqizhixin.com/articles/2024-02-15-6?from=synced\u0026keyword=%E5%88%86%E5%B8%83%E5%BC%8F%E5%BC%BA%E5%8C%96%E5%AD%A6%E4%B9%A0\n- https://joseluisc99.github.io/posts/distributed-reinforcement-learning-a-draft/\n\n## Distributed Framework\n\n\\[1\\] Massively Parallel Methods for Deep Reinforcement Learning (SGD, first distributed architecture, Gorilla DQN).\n\n\\[2\\] Asynchronous Methods for Deep Reinforcement Learning (SGD, A3C).\n\n\\[3\\] Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU (A3C on GPU).\n\n\\[4\\] Efficient Parallel Methods for Deep Reinforcement Learning (Batched A2C, GPU).\n\n\\[5\\] Evolution Strategies as a Scalable Alternative to Reinforcement Learning (ES).\n\n\\[6\\] Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for\nReinforcement Learning (ES).\n\n\\[7\\] RLlib: Abstractions for Distributed Reinforcement Learning (Library)\n\n\\[8\\] Distributed Deep Reinforcement Learning: Learn how to play Atari games in 21 minutes (Batched A3C).\n\n\\[9\\] Distributed Prioritized Experience Replay (Ape-X, distributed replay buffer).\n\n\\[10\\] IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures (CPU+GPU).\n\n\\[11\\] Accelerated Methods for Deep Reinforcement Learning (Simulation Acceleration).\n\n\\[12\\] GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning (Simulation Acceleration).\n\n\\[13\\] DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames (DD-PPO)\n\n\\[14\\] Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning (Sample Factory)\n\n\\[15\\] SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference (SEED RL)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjianzhnie%2Fscalerl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjianzhnie%2Fscalerl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjianzhnie%2Fscalerl/lists"}